planning-suite

Create slash command aliases or list existing aliases

Discover and integrate knowledge files from project and user directories

Performance analysis and optimization recommendations

Remove slash command aliases

Researches and compares technology options with structured analysis. **AUTOMATICALLY INVOKE** when user mentions: - "which tech", "compare options", "technology stack", "what should I use" - "framework comparison", "library choice", "tech recommendation" - Choosing between multiple technologies or frameworks **STRONGLY RECOMMENDED** for: - Technology stack decisions - Framework selection - Tool comparisons - Architecture planning

Automated code refactoring agent for improving code quality and structure. **AUTOMATICALLY INVOKE** this agent when user mentions "refactor", "cleanup", "technical debt", "DRY", or when detecting code duplication. **STRONGLY RECOMMENDED** for legacy code modernization, performance optimization, and maintainability improvements.

Create isolated git worktrees for parallel development, enabling multiple subagents to work concurrently on different features without conflicts or directory changes. **AUTOMATICALLY INVOKE** this agent when user mentions "parallel development", "concurrent agents", "isolated workspace", or when spawning multiple feature-developers. **STRONGLY RECOMMENDED** for multi-feature work, risky operations, and CI/CD workflows.

Implements a single delivery-agent task from an approved plan: reads the task envelope (a runtime header plus one paragraph of guidance), infers purpose / what-to-do / DoD from it, executes the work to completion (no mid-task pauses), spawns specialist sub-agents when needed, commits a single squashed commit on the worktree branch, and self-merges to MERGE_TARGET via rebase-retry on chain-tail and standalone tasks. AUTOMATICALLY INVOKE via subagent_type: "delivery-agent" — only dispatched by the schedule-plan-tasks skill, never directly by the user. NOT for: ad-hoc one-off coding tasks (use feature-developer), exploratory investigation (use Explore), code review (use code-reviewer).

Deploys code through the deployment pipeline. **AUTOMATICALLY INVOKE** when user mentions: - "deploy", "release", "ship", "launch", "go live", "push to prod" - "promote to staging", "promote to production" - After feature merge to main branch **STRONGLY RECOMMENDED** for: - Feature releases - Hotfix deployments - Rollbacks

Design system architecture and make technology decisions. Dispatches to system-architect agent for comprehensive design work. AUTOMATICALLY INVOKE when: - "design architecture", "what tech stack", "system design" - "how should I structure", "architecture for", "design system" - "technology recommendation", "compare frameworks" NOT for: Implementation (use superpowers:executing-plans), task breakdown (use superpowers:writing-plans)

Dual-perspective Node.js/TypeScript plan review (TypeScript/API + Node runtime) with iterative convergence loop. 36 Node/TS-specific questions (N20/N21 naming+docs deferred to L1's Q-G6/Q-G7 which cover these universally). **AUTOMATICALLY INVOKE** when: - Any plan exists for Node.js or TypeScript changes - Plan references package.json, tsconfig.json, .ts files, npm/yarn/pnpm/bun - Plan targets Express, Fastify, NestJS, Next.js, or similar Node frameworks - Plan modifies async code, environment variables, or Node process lifecycle - User says "review plan", "check plan", "node-plan" **NOT for:** GAS plans (use /gas-plan), code review (use /review), non-Node plans

Refactor code for improved quality and structure. Dispatches to code-refactor agent for large multi-file refactoring operations. AUTOMATICALLY INVOKE when: - "refactor this", "clean up", "reduce duplication", "DRY this up" - "simplify", "modernize", "restructure" - When detecting code duplication or technical debt NOT for: Bug fixes (fix the bug directly), feature additions (use superpowers:executing-plans)

Analyzes an approved plan and decomposes it into a dependency-ordered task graph via a two-phase TaskCreate and TaskUpdate pass. Detects linear DEPENDS ON chains (shared worktree), identifies independent work streams (parallelized), and executes the full worktree-isolated run. Also handles Branch B (learnings from session context). **AUTOMATICALLY INVOKE** when: - ExitPlanMode hook triggers (PostToolUse) - User says "schedule tasks", "create task graph", "decompose plan into tasks", "execute plan" - /schedule-plan-tasks is invoked **References:** JIT-loaded from `${CLAUDE_SKILL_DIR}/references/`

Execute a delivery-agent fixture through an actual agent dispatch and print the full response. Supports --dry-run for safe simulation.

2 hooks across 2 events